Topic > A new algorithm to solve the fractured domain problem

II. NEUROEVOLUTIONNeuroevolution is a form of machine learning that uses evolution as another form of adaptation in addition to learning. The evolutions of the ANN occur via evolutionary algorithms (EA). These evolutionary algorithms have the role of performing various tasks, such as rule extraction, connection weight training architecture design, and so on. All these processes lead to the adaptability of the evolved ANN to changes in the surrounding environment and also to adaptation to the environment itself. Over the years, several evolutionary algorithms have been developed. The developments of these evolutionary algorithms are based on a specific framework as shown in Figure 9. The various dialects of evolutionary algorithms differ only in technical details. A typical example of the difference between EAs are candidate solutions: finite alphabet strings in genetic algorithms (GA) [4], real-valued vectors in evolution strategies (ES) [5], and trees in genetic programming (GP) [ 6]. The call for evolution has become apparent as it seems suited to some of the most pressing computational problems in many fields. These problems involve the exploration of an enormous number of solution possibilities. An example is the classification of large volumes of information and also the processing of high dimensionality [7]. The above problem benefits enormously from the effective use of parallelism, whereby several paths are explored simultaneously efficiently. Finally, real world problems are too complex and are fractal in nature. Therefore, it is quite difficult to come up with a program to address these real-world problems. Handwritten computer programs are mostly limited to structural boundaries, t...... middle of paper.......[10] 10. J.D. Radcliff, “Gene set recombination and its applications for neural network topology optimization,” Neural Computing and Applications, vol. 1(1), pp. 67-90, 1993.[11] 11. S. Haykin, “Neural Networks: A Comprehensive Foundation,” Upper Saddle River, NJ: Prentice Hall, 1994.[12] 12. RKL Venkateswarlu, RV Kumari and Jayashri, Speech recognition using radial basis neural network, International Conference on Electronics and Information Technology, Vol.3, pp. 441-445, 2011.[13] 13. S. Lucas and J. Togelius. Point-to-point car racing: An initial study of evolution with respect to temporal difference learning. In IEEE Symposium on Computational Intelligence and Games, pp. 260–267, 2007.[14] 14. M. Jakobsen, “Learning to Race in a Simulated Environment,” [ONLINE], available at: http://www.hiof.no/neted/upload/attachment/site/group12/Morgan_Jakobsen_